A pipelined data processor comprises a circuit (3) for extracting two instructions into a pair of instruction registers (l, 2), a circuit (6) for detecting whether those instructions are a combination of an instruction requesting a use of an operation unit and an instruction requesting the use of other resource, and a circuit (4) to control the execution of the instruction when the decision of the detection circuit is affirmative such that those instructions are executed by the operation unit and the resource in a plurality of stages.

Pipelined data processor capable of decoding and executing plural instructions in parallel

The present invention provides for the updating of both the instructions in a branch prediction cache and instructions recently provided to an instruction pipeline from the cache when an instruction being executed attempts to change such instructions ("Store-Into-Instruction-Stream"). The branch prediction cache (BPC) includes a tag identifying the address of instructions causing a branch, a record of the target address which was branched to on the last occurrence of each branch instruction, and a copy of the first several instructions beginning at this target address. A separate instruction cache is provided for normal execution of instructions, and all of the instructions written into the branch prediction cache from the system bus must also be stored in the instruction cache. The instruction cache monitors the system bus for attempts to write to the address of an instruction contained in the instruction cache. Upon such a detection, that entry in the instruction cache is invalidated, and the corresponding entry in the branch prediction cache is invalidated. A subsequent attempt to use an instruction in the branch prediction cache which has been invalidated will detect that it is not valid, and will instead go to main memory to fetch the instruction, where it has been modified.

Method and apparatus for store-into-instruction-stream detection and maintaining branch prediction cache consistency

In a parallel data processing system having a plurality of separately operating arithmetic processing units, a method and apparatus allows a plurality of branch instructions to be operated upon in a single machine cycle. The branch instructions have associated therewith a hierarchical priority system and the method and apparatus determine which branch, if any, should be taken. In particular, the method and apparatus simultaneously determine, during the parallel execution of the branch instructions, whether any branch test condition associated with a branch instruction is true, and independently, the target address for each branch instruction and a fall-through instruction address if a branch instruction is not taken.

Hierarchical priority branch handling for parallel execution in a parallel processor

An improved branch prediction cache (BPC) scheme that utilizes a hybrid cache structure. The BPC provides two levels of branch information caching. The fully associative first level BPC is a shallow but wide structure (36 32-byte entries), which caches full prediction information for a limited number of branch instructions. The second direct mapped level BPC is a deep but narrow structure (256 2-byte entries), which caches only partial prediction information, but does so for a much larger number of branch instructions. As each branch instruction is fetched and decoded, its address is used to perform parallel look-ups in the two branch prediction caches.

Two-level branch prediction cache

A streamlined instruction processor processes data in response to a program composed of prespecified instructions in pipeline cycles. The processor comprises an instruction fetch unit, including an instruction interface adapted for connection to an instruction memory and for fetching instructions from the instruction memory. The instruction fetch unit includes an instruction prefetch buffer coupled to the instruction interface for buffering a sequence of instructions supplied to the instruction interface. A branch target cache is coupled with the prefetch buffer for storing sets of instructions retrieved from a corresponding set of locations in the instruction memory, having sequential instruction addresses. The first instruction in each such set is a branch target instruction in the program. In addition, an execution unit including a data interface adapted for connection to the data memory, executes the instructions in pipeline cycles. The execution unit includes a storage facility, coupled to the data interface, for storing data in a file of data locations identified by file addresses. The storage facility includes at least two read ports and one write port operable in response to file addresses. An addressing unit coupled to receive the instructions from the instruction register, supplies the file addresses to the read ports and the write port under program control. In addition, the addressing unit is operable in response to a stack pointer providing dynamic allocation of the file of data locations to processes within the program. A memory management unit is coupled to the data interface. The memory management unit includes an address interface adapted for connection to the data memory and the instruction memory for supplying instruction addresses to the instruction memory and data addresses to the data memory, in a simple single access mode, a pipeline mode and a burst mode.

Streamlined instruction processor

Method and apparatus for prefetching instructions for a pipelined central processor unit for a general purpose digital data processing system. A table is maintained for purposes of predicting the target addresses of transfer and indirect instructions based on past history of the execution of those instructions. The prefetch mechanism forms instruction addresses and fetches instructions in parallel with the execution of previously fetched instructions by a central execution pipeline unit of the central processor unit. As instructions are prefetched, the transfer and indirect prediction (TIP) table is checked to determine the past history of those instructions. If no transfers or indirects are found, the prefetch proceeds sequentially. If transfer or indirect instructions are found, then the prefetch uses information in the TIP table to begin fetching the target instruction(s). The purpose of the prediction of target addresses is so that in the usual case instructions following a transfer can be executed at a rate of one instruction per pipeline cycle regardless of the pipeline depth or the frequency of transfers. Instructions are fetched two words at a time in order that the instruction fetch unit can stay ahead of the central execution pipeline. An instruction stack is provided for purposes of buffering double words of instructions fetched by the instruction fetch unit while waiting for execution by the central execution pipeline unit. The TIP table is updated based upon the actual execution of instructions by the central execution pipeline unit, and the correctness of the TIP table predictions is checked during execution of every instruction.

Method and apparatus for prefetching instructions for a central execution pipeline unit

Prefetching instructions for a pipelined CPU. A TIP (transfer and indirect prediction) table 42 predicting the target address of transfer and indirect instructions based on past history of the execution of those instructions. The prefetch mechanism forms instruction addresses and fetches instructions in parallel with the execution of previously fetched instructions by a central execution pipeline unit (CEPU) 12 of the CPU. As instructions are prefetched, the TIP table is checked to determine the past history of those instructions. If no transfers or indirects are found, the prefetch proceeds sequentially. If transfer or indirect instructions are found, then the prefetch uses information in the TIP table to begin fetching the target instruction(s). The target addresses are predicted so that in the usual case instructions following a transfer can be executed at a rate of 1 instruction per pipeline cycle regardless of the pipeline depth or the frequency of transfers. Instructions are fetched 2 words at a time, so that the instruction fetch unit (IFU) 10 can stay ahead of the CEPU. An instruction stack 20 buffers double words of instructions fetched by the IFU while waiting for execution by the CEPU. The TIP table is updated based upon the actual execution of instructions by the CEPU, and the correctness of the TIP table predictions is checked during execution of every instruction.

Prefetching instructions in computer

METHOD AND APPARATUS FOR PREFETCHING INSTRUCTIONS A B S T R A C T Method and apparatus for prefetching instructions for a pipelined central processor unit for a general purpose digital data processing system. A table is maintained for purposes of predicting the target addresses of transfer and indirect instructions based on past history of the execution of those instructions. The prefetch mechanism forms instruction addresses and fetches instructions in parallel with the execution of previously fetched instructions by a central execution pipeline unit of the central processor unit. As instructions are prefetched, the transfer and indirect prediction (TIP) table is checked to determine the past history of those instructions. If no transfers or indirects are found, the prefetch proceeds sequentially. If tranfer or indirect instructions are found, then the prefetch uses information in the TIP table to begin fetching the target instruction (s). The purpose of the prediction of target addresses is so that in the usual case instructions following a transfer can be executed at a rate of one instruction per pipeline cycle regardless of the pipeline depth or the frequency of transfers. Instructions are fetched two words at a time in order that the instruction fetch unit can stay ahead of the central execution pipeline. An instruction stack is provided for purposes of buffering double words of instructions fetched by the instruction fetch unit while waiting for execution by the central execution pipeline unit. The TIP table is updated based upon the actual execution of instructions by the central execution pipeline unit, and the correctness of the TIP table predictions is checked during execution of every instruction.

Gary R. Presley-Nelson

Papers

Method and apparatus for prefetching instructions for a central execution pipeline unit

Prefetching instructions in computer

Method and apparatus for prefetching instructions

Befehlsvorgriff in einem rechner.